30 秒でわかる
Matthew Berman shows a brief experiment in which DeepSeek V4.1 Flash uses a browser-based painting tool to recreate his headshot. He finds the result recognizable and stylized but lacking detail and layered brushwork.
- 1The referenceBerman supplies a headshot and lets DeepSeek V4.1 Flash use a Paint-like website.
- 2The resultThe displayed output is an abstract, stylized version of the headshot.
- 3Missing detailBerman says the model did not reproduce the layered brushstroke technique he had in mind.
ポイント
- The experiment uses a reference headshot and a website resembling Microsoft Paint.
- Berman judges the resulting portrait stylized but lacking detail.
- A single example does not establish general portrait-painting performance.
チャプターごとに整えた全文を読む
A browser-painting experiment
Berman introduces the reference image and the tool used by DeepSeek V4.1 Flash. He then assesses the resulting portrait.
Here is the reference headshot. I let DeepSeek V4.1 Flash use a website that replicates the basic functionality of Microsoft Paint, then compare the resulting portrait with the original. The short video does not show the complete setup or a controlled comparison.
The result is not bad: it is a very stylized, abstract version of my headshot. But it lacks detail, and I think the model did not reproduce the technique of building up one brushstroke over another. That judgment applies to this particular attempt.
同じチャンネルの記事
34:21EN
Matthew Berman· 2026年10月27日Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.
0:26ENMatthew Berman· 2026年10月25日Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.
0:36ENMatthew Berman· 2026年10月25日Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.
0:21ENMatthew Berman· 2026年10月24日An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.
25:50ENMatthew Berman· 2026年10月24日Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.
32:20ENMatthew Berman· 2026年10月23日Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.